Yea the speed is nuts but I have a feeling that is because it is not seeing the demand yet. It is some monster provider with huge infra (openAI perhaps) testing out their model before release.

Reply to this note

Please Login to reply.

Discussion

I see "openAI perhaps" but on your website you attribute it clearly to openAI at https://api.ppq.ai/models

How do you not know? What would be the api endpoint to try it out without going through ppq? I'm having size issues. Some 403819 bytes queries run into issues with this and other models that should support a million tokens.

I think we get the "owned_by" from openrouter in this case as we are pulling the model from there.

I'm curious if a query that fails via us will work with openrouter. If so, that clearly points to some problem we have with how we are routing things.

I would need an account with openrouter i suppose but as horizon is so stealthy, maybe I can use it more directly without account?